[Bio] / Sprout / Sprout.pm Repository:
ViewVC logotype

Diff of /Sprout/Sprout.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.12, Wed May 4 03:24:43 2005 UTC revision 1.32, Wed Sep 14 13:24:14 2005 UTC
# Line 70  Line 70 
70    
71  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)  * B<maxSequenceLength> maximum number of residues per sequence, (default C<8000>)
72    
73    * B<noDBOpen> suppresses the connection to the database if TRUE, else FALSE
74    
75  =back  =back
76    
77  For example, the following constructor call specifies a database named I<Sprout> and a user name of  For example, the following constructor call specifies a database named I<Sprout> and a user name of
# Line 86  Line 88 
88          # Compute the options. We do this by starting with a table of defaults and overwriting with          # Compute the options. We do this by starting with a table of defaults and overwriting with
89          # the incoming data.          # the incoming data.
90          my $optionTable = Tracer::GetOptions({          my $optionTable = Tracer::GetOptions({
91                                             dbType               => 'mysql',                     # database type                         dbType       => $FIG_Config::dbms,
92                                             dataDir              => 'Data',                      # data file directory                                                          # database type
93                                             xmlFileName  => 'SproutDBD.xml', # database definition file name                         dataDir      => $FIG_Config::sproutData,
94                                             userData             => 'root/',                     # user name and password                                                          # data file directory
95                                             port                 => 0,                           # database connection port                         xmlFileName  => "$FIG_Config::sproutData/SproutDBD.xml",
96                                                            # database definition file name
97                           userData     => "$FIG_Config::dbuser/$FIG_Config::dbpass",
98                                                            # user name and password
99                           port         => $FIG_Config::dbport,
100                                                            # database connection port
101                                             maxSegmentLength => 4500,            # maximum feature segment length                                             maxSegmentLength => 4500,            # maximum feature segment length
102                                             maxSequenceLength => 8000,           # maximum contig sequence length                                             maxSequenceLength => 8000,           # maximum contig sequence length
103                           noDBOpen     => 0,               # 1 to suppress the database open
104                                            }, $options);                                            }, $options);
105          # Get the data directory.          # Get the data directory.
106          my $dataDir = $optionTable->{dataDir};          my $dataDir = $optionTable->{dataDir};
# Line 100  Line 108 
108          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;          $optionTable->{userData} =~ m!([^/]*)/(.*)$!;
109          my ($userName, $password) = ($1, $2);          my ($userName, $password) = ($1, $2);
110          # Connect to the database.          # Connect to the database.
111          my $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName, $password, $optionTable->{port});      my $dbh;
112        if (! $optionTable->{noDBOpen}) {
113            $dbh = DBKernel->new($optionTable->{dbType}, $dbName, $userName,
114                                    $password, $optionTable->{port});
115        }
116          # Create the ERDB object.          # Create the ERDB object.
117          my $xmlFileName = "$optionTable->{xmlFileName}";          my $xmlFileName = "$optionTable->{xmlFileName}";
118          my $erdb = ERDB->new($dbh, $xmlFileName);          my $erdb = ERDB->new($dbh, $xmlFileName);
# Line 420  Line 432 
432          # Loop through the incoming table names.          # Loop through the incoming table names.
433          for my $tableName (@{$tableList}) {          for my $tableName (@{$tableList}) {
434                  # Find the table's file.                  # Find the table's file.
435                  my $fileName = "$dataDir/$tableName";          my $fileName = LoadFileName($dataDir, $tableName);
436                  if (! -e $fileName) {          if (! $fileName) {
437                          $fileName = "$fileName.dtx";              Trace("No load file found for $tableName in $dataDir.") if T(0);
438                  }          } else {
439                  # Attempt to load this table.                  # Attempt to load this table.
440                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);                  my $result = $erdb->LoadTable($fileName, $tableName, $truncateFlag);
441                  # Accumulate the resulting statistics.                  # Accumulate the resulting statistics.
442                  $retVal->Accumulate($result);                  $retVal->Accumulate($result);
443          }          }
444        }
445          # Return the statistics.          # Return the statistics.
446          return $retVal;          return $retVal;
447  }  }
# Line 570  Line 583 
583  =item RETURN  =item RETURN
584    
585  Returns a list of the feature's contig segments. The locations are returned as a list in a list  Returns a list of the feature's contig segments. The locations are returned as a list in a list
586  context and as a space-delimited string in a scalar context.  context and as a comma-delimited string in a scalar context.
587    
588  =back  =back
589    
# Line 609  Line 622 
622                  }                  }
623                  # Remember this specifier for the adjacent-segment test the next time through.                  # Remember this specifier for the adjacent-segment test the next time through.
624                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);                  ($prevContig, $prevBeg, $prevDir, $prevLen) = ($contigID, $beg, $dir, $len);
625            # Compute the initial base pair.
626            my $start = ($dir eq "+" ? $beg : $beg + $len - 1);
627                  # Add the specifier to the list.                  # Add the specifier to the list.
628                  push @retVal, "${contigID}_$beg$dir$len";                  push @retVal, "${contigID}_$beg$dir$len";
629          }          }
630          # Return the list in the format indicated by the context.          # Return the list in the format indicated by the context.
631          return (wantarray ? @retVal : join(' ', @retVal));      return (wantarray ? @retVal : join(',', @retVal));
632  }  }
633    
634  =head3 ParseLocation  =head3 ParseLocation
# Line 752  Line 767 
767                  # the start point is the ending. Note that in the latter case we must reverse the DNA string                  # the start point is the ending. Note that in the latter case we must reverse the DNA string
768                  # before putting it in the return value.                  # before putting it in the return value.
769                  my ($start, $stop);                  my ($start, $stop);
770            Trace("Parsed location is $beg$dir$len.") if T(SDNA => 4);
771                  if ($dir eq "+") {                  if ($dir eq "+") {
772                          $start = $beg;                          $start = $beg;
773                          $stop = $beg + $len - 1;                          $stop = $beg + $len - 1;
774                  } else {                  } else {
775                          $start = $beg + $len + 1;              $start = $beg - $len + 1;
776                          $stop = $beg;                          $stop = $beg;
777                  }                  }
778            Trace("Looking for sequences containing $start through $stop.") if T(SDNA => 4);
779                  my $query = $self->Get(['IsMadeUpOf','Sequence'],                  my $query = $self->Get(['IsMadeUpOf','Sequence'],
780                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .                          "IsMadeUpOf(from-link) = ? AND IsMadeUpOf(start-position) + IsMadeUpOf(len) > ? AND " .
781                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",                          " IsMadeUpOf(start-position) <= ? ORDER BY IsMadeUpOf(start-position)",
# Line 770  Line 787 
787                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',                                  $sequence->Values(['IsMadeUpOf(start-position)', 'Sequence(sequence)',
788                                                                     'IsMadeUpOf(len)']);                                                                     'IsMadeUpOf(len)']);
789                          my $stopPosition = $startPosition + $sequenceLength;                          my $stopPosition = $startPosition + $sequenceLength;
790                Trace("Sequence is from $startPosition to $stopPosition.") if T(SDNA => 4);
791                          # Figure out the start point and length of the relevant section.                          # Figure out the start point and length of the relevant section.
792                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);                          my $pos1 = ($start < $startPosition ? 0 : $start - $startPosition);
793                          my $len = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;              my $len1 = ($stopPosition <= $stop ? $stopPosition : $stop) - $startPosition - $pos1;
794                Trace("Position is $pos1 for length $len1.") if T(SDNA => 4);
795                          # Add the relevant data to the location data.                          # Add the relevant data to the location data.
796                          $locationDNA .= substr($sequenceData, $pos1, $len);              $locationDNA .= substr($sequenceData, $pos1, $len1);
797                  }                  }
798                  # Add this location's data to the return string. Note that we may need to reverse it.                  # Add this location's data to the return string. Note that we may need to reverse it.
799                  if ($dir eq '+') {                  if ($dir eq '+') {
800                          $retVal .= $locationDNA;                          $retVal .= $locationDNA;
801                  } else {                  } else {
802                          $locationDNA = join('', reverse split //, $locationDNA);              $retVal .= FIG::reverse_comp($locationDNA);
                         $retVal .= $locationDNA;  
803                  }                  }
804          }          }
805          # Return the result.          # Return the result.
# Line 1230  Line 1248 
1248    
1249  =item RETURN  =item RETURN
1250    
1251  Returns a reference to a hash that maps the IDs of the incoming features to the IDs of  Returns a reference to a hash that maps the IDs of the incoming features to the best hits
1252  their best hits.  on the target genome.
1253    
1254  =back  =back
1255    
# Line 1259  Line 1277 
1277          return \%retVal;          return \%retVal;
1278  }  }
1279    
1280    =head3 SimList
1281    
1282    C<< my %similarities = $sprout->SimList($featureID, $count); >>
1283    
1284    Return a list of the similarities to the specified feature.
1285    
1286    Sprout does not support real similarities, so this method just returns the bidirectional
1287    best hits.
1288    
1289    =over 4
1290    
1291    =item featureID
1292    
1293    ID of the feature whose similarities are desired.
1294    
1295    =item count
1296    
1297    Maximum number of similar features to be returned, or C<0> to return them all.
1298    
1299    =back
1300    
1301    =cut
1302    #: Return Type %;
1303    sub SimList {
1304        # Get the parameters.
1305        my ($self, $featureID, $count) = @_;
1306        # Ask for the best hits.
1307        my @lists = $self->GetAll(['IsBidirectionalBestHitOf'],
1308                                  "IsBidirectionalBestHitOf(from-link) = ? ORDER BY IsBidirectionalBestHitOf(score) DESC",
1309                                  [$featureID], ['IsBidirectionalBestHitOf(to-link)', 'IsBidirectionalBestHitOf(score)'],
1310                                  $count);
1311        # Create the return value.
1312        my %retVal = ();
1313        for my $tuple (@lists) {
1314            $retVal{$tuple->[0]} = $tuple->[1];
1315        }
1316        # Return the result.
1317        return %retVal;
1318    }
1319    
1320    
1321    
1322    =head3 IsComplete
1323    
1324    C<< my $flag = $sprout->IsComplete($genomeID); >>
1325    
1326    Return TRUE if the specified genome is complete, else FALSE.
1327    
1328    =over 4
1329    
1330    =item genomeID
1331    
1332    ID of the genome whose completeness status is desired.
1333    
1334    =item RETURN
1335    
1336    Returns TRUE if the genome is complete, FALSE if it is incomplete, and C<undef> if it is
1337    not found.
1338    
1339    =back
1340    
1341    =cut
1342    #: Return Type $;
1343    sub IsComplete {
1344        # Get the parameters.
1345        my ($self, $genomeID) = @_;
1346        # Declare the return variable.
1347        my $retVal;
1348        # Get the genome's data.
1349        my $genomeData = $self->GetEntity('Genome', $genomeID);
1350        if ($genomeData) {
1351            # The genome exists, so get the completeness flag.
1352            ($retVal) = $genomeData->Value('complete');
1353        }
1354        # Return the result.
1355        return $retVal;
1356    }
1357    
1358  =head3 FeatureAliases  =head3 FeatureAliases
1359    
1360  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>  C<< my @aliasList = $sprout->FeatureAliases($featureID); >>
# Line 1349  Line 1445 
1445  sub CoupledFeatures {  sub CoupledFeatures {
1446          # Get the parameters.          # Get the parameters.
1447          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
1448          # Create a query to retrieve the functionally-coupled features. Note that we depend on the      # Create a query to retrieve the functionally-coupled features.
1449          # fact that the functional coupling is physically paired. If (A,B) is in the database, then      my $query = $self->Get(['ParticipatesInCoupling', 'Coupling'],
1450          # (B,A) will also be found.                             "ParticipatesInCoupling(from-link) = ?", [$featureID]);
         my $query = $self->Get(['IsClusteredOnChromosomeWith'],  
                                                    "IsClusteredOnChromosomeWith(from-link) = ?", [$featureID]);  
1451          # This value will be set to TRUE if we find at least one coupled feature.          # This value will be set to TRUE if we find at least one coupled feature.
1452          my $found = 0;          my $found = 0;
1453          # Create the return hash.          # Create the return hash.
1454          my %retVal = ();          my %retVal = ();
1455          # Retrieve the relationship records and store them in the hash.          # Retrieve the relationship records and store them in the hash.
1456          while (my $clustering = $query->Fetch()) {          while (my $clustering = $query->Fetch()) {
1457                  my ($otherFeatureID, $score) = $clustering->Values(['IsClusteredOnChromosomeWith(to-link)',          # Get the ID and score of the coupling.
1458                                                                      'IsClusteredOnChromosomeWith(score)']);          my ($couplingID, $score) = $clustering->Values(['Coupling(id)',
1459                                                            'Coupling(score)']);
1460            # The coupling ID contains the two feature IDs separated by a space. We use
1461            # this information to find the ID of the other feature.
1462            my ($fid1, $fid2) = split / /, $couplingID;
1463            my $otherFeatureID = ($featureID eq $fid1 ? $fid2 : $fid1);
1464            # Attach the other feature's score to its ID.
1465                  $retVal{$otherFeatureID} = $score;                  $retVal{$otherFeatureID} = $score;
1466                  $found = 1;                  $found = 1;
1467          }          }
# Line 1374  Line 1474 
1474          return %retVal;          return %retVal;
1475  }  }
1476    
1477    =head3 CouplingEvidence
1478    
1479    C<< my @evidence = $sprout->CouplingEvidence($peg1, $peg2); >>
1480    
1481    Return the evidence for a functional coupling.
1482    
1483    A pair of features is considered evidence of a coupling between two other
1484    features if they occur close together on a contig and both are similar to
1485    the coupled features. So, if B<A1> and B<A2> are close together on a contig,
1486    B<B1> and B<B2> are considered evidence for the coupling if (1) B<B1> and
1487    B<B2> are close together, (2) B<B1> is similar to B<A1>, and (3) B<B2> is
1488    similar to B<A2>.
1489    
1490    The score of a coupling is determined by the number of pieces of evidence
1491    that are considered I<representative>. If several evidence items belong to
1492    a group of genomes that are close to each other, only one of those items
1493    is considered representative. The other evidence items are presumed to be
1494    there because of the relationship between the genomes rather than because
1495    the two proteins generated by the features have a related functionality.
1496    
1497    Each evidence item is returned as a three-tuple in the form C<[>I<$peg1a>C<,>
1498    I<$peg2a>C<,> I<$rep>C<]>, where I<$peg1a> is similar to I<$peg1>, I<$peg2a>
1499    is similar to I<$peg2>, and I<$rep> is TRUE if the evidence is representative
1500    and FALSE otherwise.
1501    
1502    =over 4
1503    
1504    =item peg1
1505    
1506    ID of the feature of interest.
1507    
1508    =item peg2
1509    
1510    ID of a feature functionally coupled to the feature of interest.
1511    
1512    =item RETURN
1513    
1514    Returns a list of 3-tuples. Each tuple consists of a feature similar to the feature
1515    of interest, a feature similar to the functionally coupled feature, and a flag
1516    that is TRUE for a representative piece of evidence and FALSE otherwise.
1517    
1518    =back
1519    
1520    =cut
1521    #: Return Type @@;
1522    sub CouplingEvidence {
1523        # Get the parameters.
1524        my ($self, $peg1, $peg2) = @_;
1525        # Declare the return variable.
1526        my @retVal = ();
1527        # Our first task is to find out the nature of the coupling: whether or not
1528        # it exists, its score, and whether the features are stored in the same
1529        # order as the ones coming in.
1530        my ($couplingID, $inverted, $score) = $self->GetCoupling($peg1, $peg2);
1531        # Only proceed if a coupling exists.
1532        if ($couplingID) {
1533            # Determine the ordering to place on the evidence items. If we're
1534            # inverted, we want to see feature 2 before feature 1 (descending); otherwise,
1535            # we want feature 1 before feature 2 (normal).
1536            Trace("Coupling evidence for ($peg1, $peg2) with inversion flag $inverted.") if T(Coupling => 4);
1537            my $ordering = ($inverted ? "DESC" : "");
1538            # Get the coupling evidence.
1539            my @evidenceList = $self->GetAll(['IsEvidencedBy', 'PCH', 'UsesAsEvidence'],
1540                                              "IsEvidencedBy(from-link) = ? ORDER BY PCH(id), UsesAsEvidence(pos) $ordering",
1541                                              [$couplingID],
1542                                              ['PCH(used)', 'UsesAsEvidence(to-link)']);
1543            # Loop through the evidence items. Each piece of evidence is represented by two
1544            # positions in the evidence list, one for each feature on the other side of the
1545            # evidence link. If at some point we want to generalize to couplings with
1546            # more than two positions, this section of code will need to be re-done.
1547            while (@evidenceList > 0) {
1548                my $peg1Data = shift @evidenceList;
1549                my $peg2Data = shift @evidenceList;
1550                Trace("Peg 1 is " . $peg1Data->[1] . " and Peg 2 is " . $peg2Data->[1] . ".") if T(Coupling => 4);
1551                push @retVal, [$peg1Data->[1], $peg2Data->[1], $peg1Data->[0]];
1552            }
1553            Trace("Last index in evidence result is is $#retVal.") if T(Coupling => 4);
1554        }
1555        # Return the result.
1556        return @retVal;
1557    }
1558    
1559    =head3 GetCoupling
1560    
1561    C<< my ($couplingID, $inverted, $score) = $sprout->GetCoupling($peg1, $peg2); >>
1562    
1563    Return the coupling (if any) for the specified pair of PEGs. If a coupling
1564    exists, we return the coupling ID along with an indicator of whether the
1565    coupling is stored as C<(>I<$peg1>C<, >I<$peg2>C<)> or C<(>I<$peg2>C<, >I<$peg1>C<)>.
1566    In the second case, we say the coupling is I<inverted>. The importance of an
1567    inverted coupling is that the PEGs in the evidence will appear in reverse order.
1568    
1569    =over 4
1570    
1571    =item peg1
1572    
1573    ID of the feature of interest.
1574    
1575    =item peg2
1576    
1577    ID of the potentially coupled feature.
1578    
1579    =item RETURN
1580    
1581    Returns a three-element list. The first element contains the database ID of
1582    the coupling. The second element is FALSE if the coupling is stored in the
1583    database in the caller specified order and TRUE if it is stored in the
1584    inverted order. The third element is the coupling's score. If the coupling
1585    does not exist, all three list elements will be C<undef>.
1586    
1587    =back
1588    
1589    =cut
1590    #: Return Type $%@;
1591    sub GetCoupling {
1592        # Get the parameters.
1593        my ($self, $peg1, $peg2) = @_;
1594        # Declare the return values. We'll start with the coupling ID and undefine the
1595        # flag and score until we have more information.
1596        my ($retVal, $inverted, $score) = (CouplingID($peg1, $peg2), undef, undef);
1597        # Find the coupling data.
1598        my @pegs = $self->GetAll(['Coupling', 'ParticipatesInCoupling'],
1599                                     "Coupling(id) = ? ORDER BY ParticipatesInCoupling(pos)",
1600                                     [$retVal], ["ParticipatesInCoupling(from-link)", "Coupling(score)"]);
1601        # Check to see if we found anything.
1602        if (!@pegs) {
1603            Trace("No coupling found.") if T(Coupling => 4);
1604            # No coupling, so undefine the return value.
1605            $retVal = undef;
1606        } else {
1607            # We have a coupling! Get the score and check for inversion.
1608            $score = $pegs[0]->[1];
1609            my $firstFound = $pegs[0]->[0];
1610            $inverted = ($firstFound ne $peg1);
1611            Trace("Coupling score is $score. First peg is $firstFound, peg 1 is $peg1.") if T(Coupling => 4);
1612        }
1613        # Return the result.
1614        return ($retVal, $inverted, $score);
1615    }
1616    
1617    =head3 CouplingID
1618    
1619    C<< my $couplingID = Sprout::CouplingID($peg1, $peg2); >>
1620    
1621    Return the coupling ID for a pair of feature IDs.
1622    
1623    The coupling ID is currently computed by joining the feature IDs in
1624    sorted order with a space. Client modules (that is, modules which
1625    use Sprout) should not, however, count on this always being the
1626    case. This method provides a way for abstracting the concept of a
1627    coupling ID. All that we know for sure about it is that it can be
1628    generated easily from the feature IDs and the order of the IDs
1629    in the parameter list does not matter (i.e. C<CouplingID("a1", "b1")>
1630    will have the same value as C<CouplingID("b1", "a1")>.
1631    
1632    =over 4
1633    
1634    =item peg1
1635    
1636    First feature of interest.
1637    
1638    =item peg2
1639    
1640    Second feature of interest.
1641    
1642    =item RETURN
1643    
1644    Returns the ID that would be used to represent a functional coupling of
1645    the two specified PEGs.
1646    
1647    =back
1648    
1649    =cut
1650    #: Return Type $;
1651    sub CouplingID {
1652        return join " ", sort @_;
1653    }
1654    
1655  =head3 GetEntityTypes  =head3 GetEntityTypes
1656    
1657  C<< my @entityList = $sprout->GetEntityTypes(); >>  C<< my @entityList = $sprout->GetEntityTypes(); >>
# Line 1435  Line 1713 
1713                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {                  if ($line =~ m/^>\s*(.+?)(\s|\n)/) {
1714                          # Here we have a new header. Store the current sequence if we have one.                          # Here we have a new header. Store the current sequence if we have one.
1715                          if ($id) {                          if ($id) {
1716                                  $retVal{$id} = uc $sequence;                  $retVal{$id} = lc $sequence;
1717                          }                          }
1718                          # Clear the sequence accumulator and save the new ID.                          # Clear the sequence accumulator and save the new ID.
1719                          ($id, $sequence) = ("$prefix$1", "");                          ($id, $sequence) = ("$prefix$1", "");
1720                  } else {                  } else {
1721                          # Here we have a data line, so we add it to the sequence accumulator.                          # Here we have a data line, so we add it to the sequence accumulator.
1722                          # First, we get the actual data out. Note that we normalize to upper              # First, we get the actual data out. Note that we normalize to lower
1723                          # case.                          # case.
1724                          $line =~ /^\s*(.*?)(\s|\n)/;                          $line =~ /^\s*(.*?)(\s|\n)/;
1725                          $sequence .= $1;                          $sequence .= $1;
# Line 1449  Line 1727 
1727          }          }
1728          # Flush out the last sequence (if any).          # Flush out the last sequence (if any).
1729          if ($sequence) {          if ($sequence) {
1730                  $retVal{$id} = uc $sequence;          $retVal{$id} = lc $sequence;
1731          }          }
1732          # Close the file.          # Close the file.
1733          close FASTAFILE;          close FASTAFILE;
# Line 1568  Line 1846 
1846  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and  The next statement inserts a C<HasProperty> relationship between feature C<fig|158879.1.peg.1> and
1847  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.  property C<4> with an evidence URL of C<http://seedu.uchicago.edu/query.cgi?article_id=142>.
1848    
1849  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence = 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>  C<< $sprout->InsertObject('HasProperty', { 'from-link' => 'fig|158879.1.peg.1', 'to-link' => 4, evidence => 'http://seedu.uchicago.edu/query.cgi?article_id=142'}); >>
1850    
1851  =over 4  =over 4
1852    
# Line 1775  Line 2053 
2053          # Get the parameters.          # Get the parameters.
2054          my ($self, $entityName, $entityID) = @_;          my ($self, $entityName, $entityID) = @_;
2055          # Check for the entity instance.          # Check for the entity instance.
2056        Trace("Checking existence of $entityName with ID=$entityID.") if T(4);
2057          my $testInstance = $self->GetEntity($entityName, $entityID);          my $testInstance = $self->GetEntity($entityName, $entityID);
2058          # Return an existence indicator.          # Return an existence indicator.
2059          my $retVal = ($testInstance ? 1 : 0);          my $retVal = ($testInstance ? 1 : 0);
# Line 1966  Line 2245 
2245          return @retVal;          return @retVal;
2246  }  }
2247    
2248    =head3 GetProperties
2249    
2250    C<< my @list = $sprout->GetProperties($fid, $key, $value, $url); >>
2251    
2252    Return a list of the properties with the specified characteristics.
2253    
2254    Properties are arbitrary key-value pairs associated with a feature. (At some point they
2255    will also be associated with genomes.) A property value is represented by a 4-tuple of
2256    the form B<($fid, $key, $value, $url)>. These exactly correspond to the parameter
2257    
2258    =over 4
2259    
2260    =item fid
2261    
2262    ID of the feature possessing the property.
2263    
2264    =item key
2265    
2266    Name or key of the property.
2267    
2268    =item value
2269    
2270    Value of the property.
2271    
2272    =item url
2273    
2274    URL of the document that indicated the property should have this particular value, or an
2275    empty string if no such document exists.
2276    
2277    =back
2278    
2279    The parameters act as a filter for the desired data. Any non-null parameter will
2280    automatically match all the tuples returned. So, specifying just the I<$fid> will
2281    return all the properties of the specified feature; similarly, specifying the I<$key>
2282    and I<$value> parameters will return all the features having the specified property
2283    value.
2284    
2285    A single property key can have many values, representing different ideas about the
2286    feature in question. For example, one paper may declare that a feature C<fig|83333.1.peg.10> is
2287    virulent, and another may declare that it is not virulent. A query about the virulence of
2288    C<fig|83333.1.peg.10> would be coded as
2289    
2290        my @list = $sprout->GetProperties('fig|83333.1.peg.10', 'virulence', '', '');
2291    
2292    Here the I<$value> and I<$url> fields are left blank, indicating that those fields are
2293    not to be filtered. The tuples returned would be
2294    
2295        ('fig|83333.1.peg.10', 'virulence', 'yes', 'http://www.somewhere.edu/first.paper.pdf')
2296        ('fig|83333.1.peg.10', 'virulence', 'no', 'http://www.somewhere.edu/second.paper.pdf')
2297    
2298    =cut
2299    #: Return Type @@;
2300    sub GetProperties {
2301        # Get the parameters.
2302        my ($self, @parms) = @_;
2303        # Declare the return variable.
2304        my @retVal = ();
2305        # Now we need to create a WHERE clause that will get us the data we want. First,
2306        # we create a list of the columns containing the data for each parameter.
2307        my @colNames = ('HasProperty(from-link)', 'Property(property-name)',
2308                        'Property(property-value)', 'HasProperty(evidence)');
2309        # Now we build the WHERE clause and the list of parameter values.
2310        my @where = ();
2311        my @values = ();
2312        for (my $i = 0; $i <= $#colNames; $i++) {
2313            my $parm = $parms[$i];
2314            if (defined $parm && ($parm ne '')) {
2315                push @where, "$colNames[$i] = ?";
2316                push @values, $parm;
2317            }
2318        }
2319        # Format the WHERE clause.
2320        my $filter = (@values > 0 ? (join " AND ", @where) : undef);
2321        # Ask for all the propertie values with the desired characteristics.
2322        my $query = $self->Get(['HasProperty', 'Property'], $filter, \@values);
2323        while (my $valueObject = $query->Fetch()) {
2324            my @tuple = $valueObject->Values(\@colNames);
2325            push @retVal, \@tuple;
2326        }
2327        # Return the result.
2328        return @retVal;
2329    }
2330    
2331  =head3 FeatureProperties  =head3 FeatureProperties
2332    
2333  C<< my @properties = $sprout->FeatureProperties($featureID); >>  C<< my @properties = $sprout->FeatureProperties($featureID); >>
# Line 2160  Line 2522 
2522  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>  C<< my %subsystems = $sprout->SubsystemsOf($featureID); >>
2523    
2524  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped  Return a hash describing all the subsystems in which a feature participates. Each subsystem is mapped
2525  to the role the feature performs.  to the roles the feature performs.
2526    
2527  =over 4  =over 4
2528    
# Line 2170  Line 2532 
2532    
2533  =item RETURN  =item RETURN
2534    
2535  Returns a hash mapping all the feature's subsystems to the feature's role.  Returns a hash mapping all the feature's subsystems to a list of the feature's roles.
2536    
2537  =back  =back
2538    
2539  =cut  =cut
2540  #: Return Type %;  #: Return Type %@;
2541  sub SubsystemsOf {  sub SubsystemsOf {
2542          # Get the parameters.          # Get the parameters.
2543          my ($self, $featureID) = @_;          my ($self, $featureID) = @_;
2544          # Use the SSCell to connect features to subsystems.      # Get the subsystem list.
2545          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],          my @subsystems = $self->GetAll(['ContainsFeature', 'HasSSCell', 'IsRoleOf'],
2546                                                                          "ContainsFeature(to-link) = ?", [$featureID],                                                                          "ContainsFeature(to-link) = ?", [$featureID],
2547                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);                                                                          ['HasSSCell(from-link)', 'IsRoleOf(from-link)']);
# Line 2187  Line 2549 
2549          my %retVal = ();          my %retVal = ();
2550          # Loop through the results, adding them to the hash.          # Loop through the results, adding them to the hash.
2551          for my $record (@subsystems) {          for my $record (@subsystems) {
2552                  $retVal{$record->[0]} = $record->[1];          my ($subsys, $role) = @{$record};
2553            if (exists $retVal{$subsys}) {
2554                push @{$retVal{$subsys}}, $role;
2555            } else {
2556                $retVal{$subsys} = [$role];
2557            }
2558          }          }
2559          # Return the hash.          # Return the hash.
2560          return %retVal;          return %retVal;
2561  }  }
2562    
2563    =head3 SubsystemList
2564    
2565    C<< my @subsystems = $sprout->SubsystemList($featureID); >>
2566    
2567    Return a list containing the names of the subsystems in which the specified
2568    feature participates. Unlike L</SubsystemsOf>, this method only returns the
2569    subsystem names, not the roles.
2570    
2571    =over 4
2572    
2573    =item featureID
2574    
2575    ID of the feature whose subsystem names are desired.
2576    
2577    =item RETURN
2578    
2579    Returns a list of the names of the subsystems in which the feature participates.
2580    
2581    =back
2582    
2583    =cut
2584    #: Return Type @;
2585    sub SubsystemList {
2586        # Get the parameters.
2587        my ($self, $featureID) = @_;
2588        # Get the list of names.
2589        my @retVal = $self->GetFlat(['ContainsFeature', 'HasSSCell'], "ContainsFeature(to-link) = ?",
2590                                    [$featureID], 'HasSSCell(from-link)');
2591        # Return the result.
2592        return @retVal;
2593    }
2594    
2595  =head3 RelatedFeatures  =head3 RelatedFeatures
2596    
2597  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>  C<< my @relatedList = $sprout->RelatedFeatures($featureID, $function, $userID); >>
# Line 2353  Line 2752 
2752  sub GetAll {  sub GetAll {
2753          # Get the parameters.          # Get the parameters.
2754          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;          my ($self, $objectNames, $filterClause, $parameterList, $fields, $count) = @_;
2755          # Create the query.      # Call the ERDB method.
2756          my $query = $self->Get($objectNames, $filterClause, $parameterList);      my @retVal = $self->{_erdb}->GetAll($objectNames, $filterClause, $parameterList,
2757          # Set up a counter of the number of records read.                                          $fields, $count);
         my $fetched = 0;  
         # Insure the counter has a value.  
         if (!defined $count) {  
                 $count = 0;  
         }  
         # Loop through the records returned, extracting the fields. Note that if the  
         # counter is non-zero, we stop when the number of records read hits the count.  
         my @retVal = ();  
         while (($count == 0 || $fetched < $count) && (my $row = $query->Fetch())) {  
                 my @rowData = $row->Values($fields);  
                 push @retVal, \@rowData;  
                 $fetched++;  
         }  
2758          # Return the resulting list.          # Return the resulting list.
2759          return @retVal;          return @retVal;
2760  }  }
# Line 2624  Line 3010 
3010      return %retVal;      return %retVal;
3011  }  }
3012    
3013    =head3 MyGenomes
3014    
3015    C<< my @genomes = Sprout::MyGenomes($dataDir); >>
3016    
3017    Return a list of the genomes to be included in the Sprout.
3018    
3019    This method is provided for use during the Sprout load. It presumes the Genome load file has
3020    already been created. (It will be in the Sprout data directory and called either C<Genome>
3021    or C<Genome.dtx>.) Essentially, it reads in the Genome load file and strips out the genome
3022    IDs.
3023    
3024    =over 4
3025    
3026    =item dataDir
3027    
3028    Directory containing the Sprout load files.
3029    
3030    =back
3031    
3032    =cut
3033    #: Return Type @;
3034    sub MyGenomes {
3035        # Get the parameters.
3036        my ($dataDir) = @_;
3037        # Compute the genome file name.
3038        my $genomeFileName = LoadFileName($dataDir, "Genome");
3039        # Extract the genome IDs from the files.
3040        my @retVal = map { $_ =~ /^(\S+)/; $1 } Tracer::GetFile($genomeFileName);
3041        # Return the result.
3042        return @retVal;
3043    }
3044    
3045    =head3 LoadFileName
3046    
3047    C<< my $fileName = Sprout::LoadFileName($dataDir, $tableName); >>
3048    
3049    Return the name of the load file for the specified table in the specified data
3050    directory.
3051    
3052    =over 4
3053    
3054    =item dataDir
3055    
3056    Directory containing the Sprout load files.
3057    
3058    =item tableName
3059    
3060    Name of the table whose load file is desired.
3061    
3062    =item RETURN
3063    
3064    Returns the name of the file containing the load data for the specified table, or
3065    C<undef> if no load file is present.
3066    
3067    =back
3068    
3069    =cut
3070    #: Return Type $;
3071    sub LoadFileName {
3072        # Get the parameters.
3073        my ($dataDir, $tableName) = @_;
3074        # Declare the return variable.
3075        my $retVal;
3076        # Check for the various file names.
3077        if (-e "$dataDir/$tableName") {
3078            $retVal = "$dataDir/$tableName";
3079        } elsif (-e "$dataDir/$tableName.dtx") {
3080            $retVal = "$dataDir/$tableName.dtx";
3081        }
3082        # Return the result.
3083        return $retVal;
3084    }
3085    
3086  =head2 Internal Utility Methods  =head2 Internal Utility Methods
3087    
3088  =head3 ParseAssignment  =head3 ParseAssignment
# Line 2699  Line 3158 
3158      return $retVal;      return $retVal;
3159  }  }
3160    
3161    =head3 AddProperty
3162    
3163    C<< my  = $sprout->AddProperty($featureID, $key, $value, $url); >>
3164    
3165    Add a new attribute value (Property) to a feature. In the SEED system, attributes can
3166    be added to almost any object. In Sprout, they can only be added to features. In
3167    Sprout, attributes are implemented using I<properties>. A property represents a key/value
3168    pair. If the particular key/value pair coming in is not already in the database, a new
3169    B<Property> record is created to hold it.
3170    
3171    =over 4
3172    
3173    =item peg
3174    
3175    ID of the feature to which the attribute is to be replied.
3176    
3177    =item key
3178    
3179    Name of the attribute (key).
3180    
3181    =item value
3182    
3183    Value of the attribute.
3184    
3185    =item url
3186    
3187    URL or text citation from which the property was obtained.
3188    
3189    =back
3190    
3191    =cut
3192    #: Return Type ;
3193    sub AddProperty {
3194        # Get the parameters.
3195        my ($self, $featureID, $key, $value, $url) = @_;
3196        # Declare the variable to hold the desired property ID.
3197        my $propID;
3198        # Attempt to find a property record for this key/value pair.
3199        my @properties = $self->GetFlat(['Property'],
3200                                       "Property(property-name) = ? AND Property(property-value) = ?",
3201                                       [$key, $value], 'Property(id)');
3202        if (@properties) {
3203            # Here the property is already in the database. We save its ID.
3204            $propID = $properties[0];
3205            # Here the property value does not exist. We need to generate an ID. It will be set
3206            # to a number one greater than the maximum value in the database. This call to
3207            # GetAll will stop after one record.
3208            my @maxProperty = $self->GetAll(['Property'], "ORDER BY Property(id) DESC", [], ['Property(id)'],
3209                                            1);
3210            $propID = $maxProperty[0]->[0] + 1;
3211            # Insert the new property value.
3212            $self->Insert('Property', { 'property-name' => $key, 'property-value' => $value, id => $propID });
3213        }
3214        # Now we connect the incoming feature to the property.
3215        $self->Insert('HasProperty', { 'from-link' => $featureID, 'to-link' => $propID, evidence => $url });
3216    }
3217    
3218    
3219    
3220  1;  1;

Legend:
Removed from v.1.12  
changed lines
  Added in v.1.32

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3